{"total":33,"rows":[{"id":"2402.12354","title":"LoRA+: Efficient Low Rank Adaptation of Large Models","created":"2024-02-19","cited_by_count":377,"area":null},{"id":"2505.01618","title":"Don't be lazy: CompleteP enables compute-efficient deep transformers","created":"2025-05-02","cited_by_count":78,"area":null},{"id":"2406.08447","title":"The Impact of Initialization on LoRA Finetuning Dynamics","created":"2024-06-12","cited_by_count":54,"area":null},{"id":"2310.02984","title":"Scaling Laws for Associative Memories","created":"2023-10-04","cited_by_count":35,"area":null},{"id":"2407.17465","title":"u-$\\mu$P: The Unit-Scaled Maximal Update Parametrization","created":"2024-07-24","cited_by_count":29,"area":null},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"area":null},{"id":"2406.06248","title":"Compute Better Spent: Replacing Dense Layers with Structured Matrices","created":"2024-06-10","cited_by_count":28,"area":null},{"id":"2512.22382","title":"Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration","created":"2025-12-26","cited_by_count":27,"area":null},{"id":"2402.17457","title":"Super Consistency of Neural Network Landscapes and Learning Rate Transfer","created":"2024-02-27","cited_by_count":23,"area":null},{"id":"2507.02119","title":"Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks","created":"2025-07-02","cited_by_count":22,"area":null},{"id":"2512.05620","title":"Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales","created":"2025-12-05","cited_by_count":21,"area":null},{"id":"2309.17310","title":"Leave-one-out Distinguishability in Machine Learning","created":"2023-09-29","cited_by_count":20,"area":null},{"id":"2312.12226","title":"On the Parameterization of Second-Order Optimization Effective Towards the Infinite Width","created":"2023-12-19","cited_by_count":15,"area":null},{"id":"2510.01938","title":"StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold","created":"2025-10-02","cited_by_count":14,"area":null},{"id":"2410.04642","title":"The Optimization Landscape of SGD Across the Feature Learning Strength","created":"2024-10-06","cited_by_count":13,"area":null},{"id":"2603.15958","title":"Deriving Hyperparameter Scaling Laws via Modern Optimization Theory","created":"2026-03-16","cited_by_count":10,"area":null},{"id":"2510.15262","title":"Robust Layerwise Scaling Rules by Proper Weight Decay Tuning","created":"2025-10-17","cited_by_count":8,"area":null},{"id":"2406.00153","title":"$\\mu$LO: Compute-Efficient Meta-Generalization of Learned Optimizers","created":"2024-05-31","cited_by_count":7,"area":null},{"id":"2512.22768","title":"Understanding the Mechanisms of Fast Hyperparameter Transfer","created":"2025-12-28","cited_by_count":7,"area":null},{"id":"2607.20548","title":"SOAP, Muon, and Beyond: Pushing LLM Pretraining Scales","created":"2026-07-13","cited_by_count":6,"area":null},{"id":"2506.00846","title":"Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2401.07085","title":"Three Mechanisms of Feature Learning in a Linear Network","created":"2024-01-13","cited_by_count":4,"area":null},{"id":"2411.02001","title":"Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation","created":"2024-11-04","cited_by_count":4,"area":null},{"id":"2601.04890","title":"Learnable Multipliers: Freeing the Scale of Language Model Matrix Layers","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2602.07697","title":"On the Infinite Width and Depth Limits of Predictive Coding Networks","created":"2026-02-07","cited_by_count":2,"area":null},{"id":"2607.14018","title":"Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth","created":"2026-07-15","cited_by_count":2,"area":null},{"id":"2606.06418","title":"Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2601.01306","title":"Towards a Principled Muon under $\\mu\\mathsf{P}$: Ensuring Spectral Conditions throughout Training","created":"2026-01-04","cited_by_count":0,"area":null},{"id":"2606.04048","title":"Unlocking Feature Learning in Gated Delta Networks at Scale","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2609.34130","title":"Training and Inference Dynamics of PLDR-LLMs: Row-Map Collapse, Renormalization, and Predictive Reduction","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.01172","title":"Learning Rate Transfer for Hybrid Transformer-SSM Architectures","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.09835","title":"A Deafening Silence: Catastrophic Forgetting Lives in the Output Embeddings of Tokens the Data Never Speaks","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.11668","title":"$\\sigma$Transfer: Uncertainty Transfer from Small to Large Networks under $\\mu\\mathrm{P}$","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}